Optimal control of LQG problem with an explicit trade-off between mean and variance.

Fucai Qian Guo Xie Ding Liu Wenfang Xie

Published in: Int. J. Syst. Sci. (2011)

Keyphrases

optimal control
trade off
bias variance
dynamic programming
control problems
control strategy
feedback control
class of nonlinear systems
reinforcement learning
infinite horizon
linear quadratic
optimal control problems
control law
optimal policy
scale space
stochastic control
special case
learning algorithm